WO2021036876A1

WO2021036876A1 - Method and device for providing live stream auxiliary data, apparatus, and readable medium

Info

Publication number: WO2021036876A1
Application number: PCT/CN2020/109952
Authority: WO
Inventors: 姜子阳
Original assignee: 北京字节跳动网络技术有限公司
Priority date: 2019-08-30
Filing date: 2020-08-19
Publication date: 2021-03-04
Also published as: CN110446057A; CN110446057B

Abstract

Disclosed are a method and device for providing live stream auxiliary data, an apparatus, and a readable medium. The method for providing live stream auxiliary data comprises: obtaining live stream auxiliary data when a streamer user is broadcasting a live video stream, wherein the live stream auxiliary data comprises at least one of the following: live stream room data pertaining to the streamer user, and fan preference data pertaining to the streamer user; and sending the live stream auxiliary data to the streamer user, such that the streamer user optimizes the current content of the live video stream according to the live stream auxiliary data.

Description

Method, device, equipment and readable medium for providing live broadcast auxiliary data

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office with an application number of 201910816836.1 on August 30, 2019. The entire content of the above application is incorporated into this application by reference.

Technical field

The present disclosure relates to the field of Internet technology, for example, to a method, device, device, and readable medium for providing live broadcast auxiliary data.

Background technique

Currently, in live video applications, anchor users can attract fans on the live broadcast platform to watch by turning on the live video function. In the process of live video, the host user not only has to complete the live broadcast of the topic type content, but also realizes the interaction with the fan users. Therefore, it is difficult to accurately discover the changes in the popularity of the live video and the reasons for the changes in the live video in real time, which will seriously affect the host. The real-time and accuracy of the user's adjustment to the subsequent live video content.

Summary of the invention

The present disclosure provides a method, device, equipment, and readable medium for providing live broadcast auxiliary data, which can provide live broadcast auxiliary data for adjusting live broadcast strategies to host users in real time, so as to help anchor users to make real-time and accurate adjustments to subsequent live video content, and attract A large number of fans increase the live broadcast enthusiasm of the anchor users.

The present disclosure provides a method for providing live broadcast auxiliary data, and the method includes:

During the live broadcast of the live video of the anchor user, the live broadcast auxiliary data is obtained; the live broadcast auxiliary data includes at least one of the following: live room data of the anchor user and the anchor fan preference data;

The live broadcast auxiliary data is sent to the anchor user, so that the anchor user optimizes the current live video content according to the live broadcast auxiliary data.

The present disclosure also provides a device for providing live broadcast auxiliary data, including:

The auxiliary data obtaining module is configured to obtain live broadcast auxiliary data during the live broadcast of the live video of the anchor user; the live broadcast auxiliary data includes at least one of the following: live room data of the anchor user and preference data of the anchor fans;

The auxiliary data sending module is configured to send the live broadcast auxiliary data to the anchor user, so that the anchor user optimizes the current live video content according to the live broadcast auxiliary data.

The present disclosure also provides an electronic device, which includes:

One or more processors;

Memory, configured to store one or more programs;

When the one or more programs are executed by the one or more processors, the one or more processors implement the method for providing live auxiliary data according to any embodiment of the present disclosure.

The present disclosure provides a readable medium on which a computer program is stored, and when the program is executed by a processor, the method for providing live broadcast auxiliary data as described in any embodiment of the present disclosure is realized.

Description of the drawings

FIG. 1 shows a flowchart of a method for providing live broadcast auxiliary data provided by an embodiment of the present disclosure;

2A-2C show a flowchart of another method for providing live broadcast auxiliary data provided by an embodiment of the present disclosure;

FIG. 3 shows a flowchart of another method for providing live broadcast auxiliary data provided by an embodiment of the present disclosure;

FIG. 4 shows a schematic structural diagram of an apparatus for providing live broadcast auxiliary data provided by an embodiment of the present disclosure;

Fig. 5 shows a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

detailed description

The present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. The steps recorded in the method embodiments of the present disclosure may be executed in a different order, and/or executed in parallel. In addition, method implementations may include additional steps and/or omit to perform the illustrated steps. The term "including" and its variations as used herein are open-ended includes, that is, "including but not limited to". The term "based on" is "based at least in part on." The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments." Related definitions of other terms will be given in the following description.

The concepts of "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. relationship.

The modifications of "a" and "a plurality" mentioned in the present disclosure are illustrative and not restrictive, and those skilled in the art should understand that unless the context clearly indicates otherwise, they should be interpreted as "one or more" . The names of messages or information exchanged between multiple parties in the embodiments of the present disclosure are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

FIG. 1 is a flowchart of a method for providing live broadcast auxiliary data provided by this embodiment. This embodiment may be applicable to a situation where the host user provides live broadcast auxiliary data for optimizing live video content during the live broadcast of the host user. The method may be executed by an apparatus for providing live broadcast auxiliary data or an electronic device. The apparatus may be implemented by at least one of software and hardware, and the apparatus may be configured in the electronic device.

Optionally, the electronic device may be a device corresponding to the back-end live broadcast platform of the application, or a mobile terminal device with an application client installed.

Optionally, as shown in FIG. 1, the method in this embodiment may include the following steps:

S101: Acquire live broadcast auxiliary data during the live broadcast of the live video of the user.

The live broadcast auxiliary data may be data that assists the host user to optimize and adjust the live video theme type, live broadcast style, and live broadcast content. The live broadcast auxiliary data may include at least one of the following: live room data of the host user and preference data of the host's fans. Optionally, the live room data of the anchor user may be data extracted from the content in the live room of the anchor user, which can assist the anchor user in adjusting the live video of the anchor user. The live broadcast room data of the host user may include: data related to the number of fans watching the current live video in the live broadcast room, for example, may include at least one of the following: the number of fans watching the current live video and the number of fans watching the current live video Changes. The live broadcast room data of the host user may also include: data related to the interactive comment content of the fans in the live broadcast room. For example, it may include at least one of the following: comments on the live video indicated by the fans in the comments (such as praise, middle Reviews or bad reviews, etc.) and the content of their preferences indicated by fans in the comments (such as preferred topic types, preferred live broadcast styles, etc.). The anchor fan preference data may be data extracted from some common characteristics possessed by the anchor user's fans, which can assist the anchor user in adjusting the live video. The anchor fan preference data may include: the theme type, the live broadcast style, and the live broadcast time period of the live broadcast that the fans of the anchor user usually like to watch.

Optionally, in the process of broadcasting the live video of the user, this step may trigger the acquisition of the live broadcast auxiliary data in real time or at a fixed time. For example, the acquisition of the live broadcast auxiliary data may be triggered every 10 minutes. Specifically, an implementable way to obtain live room data of an anchor user may be to analyze the number of fans in the live room from the dimension analysis, monitor the statistics process of the number of viewers in the live room of the anchor user in real time, and obtain the number of real-time fans in the live room as The live room data of the host user; it can also be the live room data of the host user by calculating the change in the number of fans (such as the number of fans increased or decreased) according to the obtained number of watching fans. Another practicable way to obtain the live room data of the host user may be to analyze the interactive comment content of the live room from the dimension of the interactive comment content of the live room, to identify the interactive comment content of the fans in the live room, and extract valuable vocabulary therefrom. The interactive comment content of the fans in the live broadcast room, for example, includes at least one of the following content: the comment content in the comment column of the live broadcast room and the barrage content on the live broadcast interface. Valuable vocabulary, for example, may be a vocabulary that expresses the evaluation of this live video, such as favorable, general, or bad reviews; it may also be a vocabulary of the favorite content expressed by the fan user in the comment content. How to perform the above-mentioned two implementable processes will be described in detail in subsequent embodiments.

Optionally, an achievable way to obtain the anchor fan preference data in this step may be to obtain the anchor user’s fan historical viewing data and operation data from the live broadcast platform, and add all the fan’s historical viewing data and operation data to fan viewing and favorites. Or the live broadcast theme type and live broadcast style with the most comments as the fan's favorite theme type and live broadcast style; the time period with the most viewing time distribution is regarded as the fan's favorite viewing time period. At this time, the determined theme type, live broadcast style, and viewing period of the fans are used as the anchor fan preference data. Another feasible way to obtain the anchor fan’s preference data can be to obtain the preference characteristic data of each fan through the portrait of each fan of the anchor user, and then conduct a comprehensive analysis of the preference characteristic data of all fans, and extract most of the anchor users’ fans from it. The shared public preference characteristic data serves as the anchor fan preference data. The specific implementation of this implementable manner will be described in detail in subsequent embodiments.

S102: Send the live broadcast auxiliary data to the anchor user, so that the anchor user optimizes the current live video content according to the live broadcast auxiliary data.

Optionally, in this embodiment, when the live broadcast auxiliary data is sent to the anchor user, the live broadcast auxiliary data may be sent to the terminal to which the anchor user belongs or the client corresponding to the anchor user account, where the live broadcast auxiliary data may be a notification Messages, receipt messages of live video, and pop-ups are sent to the anchor user. After receiving the live broadcast auxiliary data, the anchor user can optimize the current live broadcast content based on the content on the live broadcast auxiliary data and combine his own live broadcast advantages to improve the quality of subsequent live broadcast videos and attract more fans.

Optionally, when sending the live broadcast auxiliary data to the host user in this step, the live broadcast auxiliary data may be directly sent to the host user, or after the live broadcast auxiliary data is standardized and integrated, the standardized integrated data is sent to Anchor users. The standardized integration processing of the live broadcast auxiliary data may be to call the program code corresponding to the data integration template, use the live broadcast auxiliary data obtained in S101 as input data, and run the data integration template. At this time, the data integration template will fill the live broadcast auxiliary data into the corresponding empty area in the data integration template to realize the standardized integration processing of the live broadcast auxiliary data. The processed live broadcast auxiliary data can more clearly and intuitively assist the anchor user to optimize the current live video content. For example, the live broadcast auxiliary data obtained by S101 can be "500, praise, song type, interactive type". Because the live broadcast auxiliary data is too abstract, the obtained live broadcast auxiliary data is directly sent to the host user, which is difficult for the host user to understand. When using the data integration template "the number of people in the live broadcast room [], the fans in the live broadcast room comment on the current live broadcast as [], the fan’s preferred theme type is [], and the fan’s preferred live broadcast style is []", the live broadcast assistance obtained by S101 The data is standardized and integrated, and the processed auxiliary data for the live broadcast is "500 people in the live broadcast room. The fans in the live broadcast room have rated the current live broadcast as positive, the fan's favorite theme type is song, and the fan's favorite live broadcast style is interactive. ".

This embodiment provides a method for providing live broadcast auxiliary data. The live broadcast auxiliary data including at least one of the following: live room data of the anchor user and fan preference data of the anchor user is obtained during the live broadcast of the live video of the anchor user, and the The live broadcast auxiliary data is sent to the anchor user, so that the anchor user optimizes the current live video content according to the live broadcast auxiliary data. The solution of this embodiment can provide live broadcast auxiliary data for adjusting the live broadcast strategy to the host user in real time to help the host user make real-time and accurate adjustments to the subsequent live video content, thereby attracting a large number of fans and increasing the live broadcast enthusiasm of the host user.

In order to ensure the comprehensiveness and accuracy of the live broadcast auxiliary data provided to the anchor user in this embodiment, when the live broadcast auxiliary data is obtained in this embodiment, not only at least one of the following introduced in S101 can be obtained: the live broadcast related to the anchor user Time data and/or anchor fan preference data can further expand the scope of the live broadcast auxiliary data acquisition, and obtain the auxiliary data related to the live broadcast platform at that time (ie, the live broadcast platform auxiliary data) together with the data obtained in S101 as the live broadcast auxiliary data. The auxiliary data of the live broadcast platform may also include, but is not limited to: at least one of the video theme distribution data in the station, the number of fans in the live broadcast room, and the fan preference data in the station.

The video topic distribution data on the site can be the total video resources owned by the live platform site, the distribution of each topic type video in the total video resources, for example, it can be the number of each topic type video, or each topic The proportion of types of videos in total video resources, etc. The way to obtain the video topic distribution data in the site can be: if the live broadcast platform has pre-calculated the distribution of each topic in the site according to the topic type of the existing videos in the live broadcast platform, that is, the video topic distribution data in the site, then the electronic The device can directly interact with the live broadcast platform to obtain the video theme distribution data on the site. It can also be that the live broadcast platform only records the relevant data of the video on the site, and does not count the distribution data of the video on the site. At this time, the electronic device can interact with the live broadcast platform to obtain the subject type of all the videos on the site from the live broadcast platform, and then count each The number of videos corresponding to each topic type is calculated, and then the distribution number or proportion of each topic type video in the site in the live platform site is calculated as the video topic distribution data in the site. Optionally, it may also be based on the video theme distribution data in the station, and the scarce theme in the station is used as the live broadcast auxiliary data, that is, as the live broadcast theme recommended for the anchor user to adjust subsequently. Among them, the scarce topic can refer to the type of video topic that is lacking in the live broadcast platform.

The number of fans in the live broadcast room of the site may be the value of the number of fans in each live room currently being broadcast by the live broadcast platform, the average number of fans, and the distribution of the number of fans, etc. The way to obtain the number of fans in the live broadcast room of the station can be: electronic equipment monitors the number of fans in each live room in the station through the live broadcast platform, and performs related processing operations on the number of fans in each live room to obtain the number of fans in the live broadcast room. . For example, it can be the average of the number of fans watching in all live broadcast rooms to obtain the average number of fans in the live broadcast room; it can also be the statistics of the distribution of the number of fans in the live broadcast room in the station to obtain the live room corresponding to each fan number interval Quantity; it can also be in other ways, which is not limited in this embodiment.

The fan preference data in the site may be data such as the type of live broadcast theme, the live broadcast style, and the live broadcast time preferred by the currently online fans in the live broadcast platform. Optionally, the preference data of the fans on the site in this embodiment may be preference data shared by most of the selected fans after the preference data of the online fans on the site are counted. The method of obtaining the fan preference data in the site may be similar to the method of obtaining the anchor fan preference data, and the specific obtaining method will be described in detail in subsequent embodiments.

In this embodiment, the live broadcast platform auxiliary data is combined with at least one of the following as the live broadcast auxiliary data: live room data of the anchor user and the anchor fan preference data. The advantage of this setting is that the auxiliary data provided to the anchor user is more comprehensive, so that The live broadcast content adjusted by the host user according to the live broadcast auxiliary data not only meets the needs of fans in the live broadcast room, but also better meets the requirements of online fans in the entire live broadcast platform, thereby attracting more fans to watch the live video.

2A-2B show a flowchart of another method for providing live broadcast assistance data provided by this embodiment; this embodiment is optimized on the basis of the optional solutions provided in the above embodiment, and how to obtain live broadcast assistance In the data, the live room data of the host user and the fan preference data of the host are introduced in detail.

Optionally, FIG. 2A shows a flowchart of an implementable manner of performing a method for providing live broadcast auxiliary data when the live broadcast auxiliary data is the live room data of the host user. The specific implementation steps include:

S201: During the live broadcast of the live video of the anchor user, monitor the number of fans in the live broadcast room where the anchor user is located.

Optionally, this step can be to monitor the viewer statistics process in the live broadcast room of the anchor user in real time or every preset time (such as 10 minutes) during the live broadcast of the live video of the anchor user, so as to obtain the current fans of the anchor user in the live broadcast room. Quantity.

S202: Determine a change in the number of viewing fans according to the number of viewing fans.

Optionally, this step may be to analyze the increase or decrease of the number of fans in the live broadcast room of the anchor user during the at least two adjacent detections based on the number of watching fans monitored at least twice in S201. There are many implementation ways to determine the change in the number of viewing fans according to the number of viewing fans, and this step is not limited. Among them, an implementable manner may be: drawing a real-time change curve graph of the number of viewing fans according to the number of viewing fans, as the change of the number of viewing fans. The X-axis of the real-time change curve graph may be the time of each monitoring of the recording S201, and the Y-axis may be the value of the number of fans watching each monitoring. The real-time change curve graph of the number of fans is used to show the change of the number of fans who watch the live broadcast of the anchor user. Another implementable manner may be: determining the change value of the number of viewing fans according to the number of viewing fans at adjacent moments, and using the change value as the change of the number of fans. Another implementable manner may also be to determine the change value of the number of viewing fans according to the number of viewing fans at adjacent moments, and if the change value exceeds the normal change range, the change value is taken as the change of the number of viewing fans . This implementable manner may be to preset a normal variation range of the number of viewing fans, such as a range of -20 to 20, where the longer the period of monitoring the number of viewing fans, the larger the normal variation range corresponding to the setting. After S201 monitors the number of watching fans in the live broadcast room where the host user is located, compare the number of watching fans monitored this time with the number of watching fans monitored last time to determine the number of watching fans monitored twice. Whether the change value of is within the normal change range, if the change value of the number of watching fans monitored twice is within the normal change range, it means that the change is an acceptable change in the number of normal fans and can be ignored; adjacent; The two monitored changes in the number of viewing fans exceed the normal range, indicating that there has been an abnormal change in the number of viewing fans at this time, and the change in the number of abnormal changes needs to be regarded as the change in the number of viewing fans. Optionally, in this step, when determining the change in the number of viewing fans, at least one of the above three possible implementation manners may be executed.

S203: Use at least one of the following as the live room data of the anchor user: the number of watching fans and the change in the number of watching fans.

Optionally, in this step, the number of watching fans monitored in S201 can be used as the live room data of the anchor user; it can also be the change in the number of watching fans determined in S202 as the live room data of the anchor user; or it can be monitored in S201 The number of watched fans and the change of the number of watched fans determined in S202 are used as the live room data of the anchor user.

S204: Send the live room data of the anchor user to the anchor user, so that the anchor user optimizes the current live video content according to the live room data of the anchor user.

Optionally, FIG. 2B shows a flowchart of another implementable manner of performing a method for providing live broadcast auxiliary data when the live broadcast auxiliary data is the live room data of the host user. The specific implementation steps include:

S205, during the live broadcast of the live video of the host user, perform at least one of the following recognition on the interactive comment content of the live broadcast room where the host user is located: text recognition and semantic recognition; determine a keyword vocabulary, the keyword vocabulary includes at least one of the following: evaluation Vocabulary and favorite content vocabulary.

Optionally, this step may be to obtain the current interactive comment content of the live broadcast room where the host user is located in real time during the live broadcast of the live video of the host user; it may also be to obtain the content within the preset time period every preset time (such as 10 minutes). The interactive comment content of the live broadcast room where the host user is located. Then, at least one of recognition is performed on the acquired interactive comment content: text recognition and semantic recognition, and the keyword vocabulary is determined. An implementable manner of the specific determination method may be to preset some candidate evaluation vocabulary and candidate preference vocabulary. For example, the preset candidate evaluation vocabulary includes: good, medium, bad, and wonderful. The pre-set candidate favorite words include: like, love, obsession, and addiction. When performing this step, you can first obtain the comment content in the comment column of the live broadcast room where the host user is located and the barrage content on the live broadcast interface as the interactive comment content of the live broadcast room, and then perform text recognition on the obtained interactive comment content, and then Perform word segmentation on the recognized text, and match each segmented vocabulary with the preset candidate evaluation vocabulary and candidate favorite vocabulary, and use the successfully matched candidate evaluation vocabulary as the evaluation vocabulary in the keywords; The suffix words of the candidate favorite words in the interactive comment content are used as the favorite content words. For example, if the favorite vocabulary that is successfully matched is "like" and the interactive comment content is "like popular songs", then the favorite suffix word "popular song" in the interactive comment content may be used as the favorite content vocabulary.

Optionally, in the case that some interactive comment content does not contain obvious evaluation vocabulary or favorite content vocabulary, this step can also adopt another implementable way to determine the keyword vocabulary. Specifically, it can be the semantics of the interactive comment content. Recognition, it is judged whether the semantics of the interactive comment content is an evaluation of the live video or content that contains fan preferences. If the semantic recognition result is an evaluation of the live video, the corresponding evaluation vocabulary is determined according to the semantic recognition result. For example, if the interactive comment content is "the song is finished, come again", although the comment content has no evaluation vocabulary, it can be seen through semantic analysis that it must be the host who sings well and the fans like to listen to it, so the host will be allowed to sing again One, so the semantic recognition result of the comment content is the evaluation of the live content, and the determined evaluation vocabulary is "good praise". Similarly, semantic recognition can also be used to extract favorite content from interactive comment content for interactive comment content that does not have obvious favorite vocabulary. For example, if the interactive comment content is "I watch every live broadcast singing", although the comment content does not have a favorite vocabulary, it can be seen from semantic analysis that fans like to listen to the anchor singing, so the determined favorite content vocabulary is "song" . Optionally, this step may be to use a pre-trained neural network model to perform semantic recognition on interactive comment content.

In order to ensure the accuracy and comprehensiveness of the keywords determined according to the content of the interactive comments, this step may simultaneously adopt the above two implementable manners to determine the keywords.

S206: Determine the weight value of the keyword according to the frequency of occurrence of the keyword in the interactive comment content.

Optionally, since there are usually more interactive content in the live broadcast room of the host user, and each fan’s evaluation of the live video and their own preferences are not necessarily the same, the number of keywords determined in S205 is usually more than one . When the keyword determined in S205 is one, the keyword can be directly used as the live room data of the host user. If the number of keywords determined in S205 is large, if all keywords are used as the live broadcast room data of the host user, it will cause more live broadcast auxiliary data and poor accuracy, which will affect the accuracy of the host user's adjustment of subsequent live broadcast content. . At this time, this step may be to count the frequency of occurrence of the keyword determined in S205 in the interactive comment content of the live broadcast room. If the frequency of occurrence of the keyword is more, the weight value corresponding to the keyword is larger. For example, the frequency of occurrence of each keyword may be directly used as the weight value of the keyword.

S207: Use the keyword vocabulary and its weight value as the live room data of the anchor user.

Optionally, this step may be to associate the keywords determined in S205 with the weight value of each keyword determined in S206 and directly use them as the live room data of the host user. For example, the keywords determined in S205 are "good reviews, bad reviews, songs and dances", and S206 sequentially determines the weight values of the above keywords to be "256, 51, 179, 3", then the keywords and the weight values can be correlated. "Good reviews-256, bad reviews-51, songs-179, dance-3" are the live room data of the anchor users. Optionally, in order for the host user to more intuitively adjust the subsequent live broadcast content according to the live room data of the host user, this embodiment can filter multiple keywords that generate the live room data of the host user to select valuable keywords As the live room data of the host user. It can be based on the keyword weight value determined in S206, the keywords determined in S205 are sorted, and one or more keywords in the top ranking are selected as the live room data of the host user. For example, the weight can be selected from the keywords. The evaluation vocabulary with the first value, the favorite content vocabulary with the first weight value, and the weight value of the two words are used as the live room data of the host user.

S208: Send the live room data of the anchor user to the anchor user, so that the anchor user optimizes the current live video content based on the live room data of the anchor user.

Optionally, FIG. 2C shows a flowchart of an implementable manner of performing a method for providing live broadcast auxiliary data when the live broadcast auxiliary data is the main broadcast fan preference data. The specific implementation steps include:

S209: Obtain detailed data of fans of the anchor user during the live broadcast of the video by the anchor user.

Optionally, the live broadcast platform of this embodiment records basic information of all users managed by the live broadcast platform and operation data on the live broadcast platform, that is, detailed data of all users. The operation data in the detailed data may be the operation performed by the user on the live broadcast platform within a certain period of time before the current moment (for example, it may be within a month). Specifically, for fan users, the operation data may include The time to watch the live video, the title of the live video, the following host users, the favorite or shared live video, etc. In this step, the electronic device can obtain the detailed data of the fans of the anchor user currently watching the live video from the live broadcast platform in real time or every preset duration (for example, 5 minutes) during the live broadcast of the live video of the anchor user.

S210: Input the detailed data of the anchor user's fan into the user portrait model to obtain the fan portrait of the anchor user's fan.

Among them, the user portrait model may be a neural network model that is trained in advance based on a large amount of sample data, and can outline the fan portrait of the fan according to the detailed information of the fan. The sample data may include a large number of detailed information of different characters and fan portraits corresponding to different characters. Fan portraits can be a tool for delineating multi-dimensional features such as attribute characteristics, behavioral characteristics, or preferences of fans, and can be abstracted into labels for each dimension, and these labels are used to accurately draw fan portraits.

Optionally, in this step, the detailed data of the anchor user's fans obtained from the live broadcast platform in S209 are used as input parameters to call and run the program code of the user portrait model. At this time, the user portrait model will be based on the input details of the anchor user's fans The data is analyzed and processed, and the fan portraits of the fans of the anchor user are drawn.

Optionally, during the live broadcast of the anchor user, the number of anchor users’ fans is relatively large. In order to improve the efficiency of generating anchor fan preference data (ie live broadcast auxiliary data), and to provide the anchor user with more valuable anchor fan preference data, In this step, the fans of the host user can be screened, high-quality fans can be selected, and fan portraits can be generated for the host user. The specific execution process may be to determine whether at least one of the ratings and consumption conditions of the anchor user's fans meets the high-quality evaluation standard; and input the detailed data of the anchor user's fans that meet the high-quality evaluation standard into the user portrait model. Among them, the high-quality evaluation standard can be a preset evaluation standard for judging whether a fan is a high-quality fan. The evaluation standard can involve multiple aspects. For example, the account level of the fan can be set to be higher than a certain preset. Fans at a level are high-quality fans; for fan consumption, fans whose consumption amount per unit time (such as one month) is higher than the preset amount are high-quality fans. At this time, this step may be based on at least one of the fan level information and consumption status information in the detail data of each fan of the host user obtained in S209, to determine at least one of the fan level and consumption status of the host user currently watching the live video. Whether it meets the high-quality evaluation criteria, if at least one of the ratings and consumption of the fans currently watching the live video of the host user meets the high-quality evaluation criteria, then input the detailed data of the fan into the user portrait model to obtain the fan portrait of the fan; if If the ratings and consumption status of the fans who currently watch the live video by the anchor user do not meet the high-quality evaluation criteria, the detailed data of the fan is ignored.

S211: Obtain preference feature data from the fan portrait.

Optionally, since the fan portrait includes tags corresponding to multiple dimensional features such as the fan’s attribute characteristics, behavior characteristics, or preference characteristics, the electronic device in this step can obtain the fan portrait of each anchor user’s fan for S210, from each In the fan portrait, the tag corresponding to the favorite feature is searched, and then the favorite feature data corresponding to the tag is obtained.

S212: Extract public preference feature data from the preference feature data as the anchor fan preference data.

Optionally, since S211 obtains preference feature data for each anchor user's fans, since each anchor user's fans have different preferences, the preference feature data obtained in S211 may not be the same. If the preference characteristics of all fans are changed The data are all used as fan preference data, and there will be a wider range of fan preference data, which greatly reduces the value of fan preference data. For example, if 100 types of anchor fan preference data are provided to anchor users, it is difficult for anchor users to obtain truly valuable data information. In view of this situation, this step may be to count the number of appearances of each preference feature data obtained in S211, and find one or more preference feature data with the most occurrences as the common preference feature data shared by most fans. Since the public preference characteristic data is valuable preference characteristic data extracted from a large amount of preference characteristic data, the public preference characteristic data can be used as the anchor fan preference data.

S213: Send the anchor fan preference data to the anchor user, so that the anchor user optimizes the current live video content according to the live room data of the anchor user.

This embodiment provides a method for providing live broadcast auxiliary data. During the process of the live broadcast of the live video of the anchor user, multi-dimensional anchor auxiliary data is obtained, that is, data related to the number of fans in the live broadcast room, and data related to the fans in the live broadcast room. At least one of interactive comment content-related data and anchor fan preference data. For each kind of live broadcast auxiliary data, different acquisition rules are set correspondingly. After the live broadcast auxiliary data is obtained in real time according to the acquisition rules of each anchor auxiliary data Sent to the host user. This helps the anchor users to make real-time and accurate adjustments to the follow-up live video content in real time, attract a large number of fans, and increase the live broadcast enthusiasm of the anchor users.

FIG. 3 shows a flowchart of another method for providing live broadcast auxiliary data provided by this embodiment; this embodiment is optimized on the basis of the optional solutions provided in the foregoing embodiment, and provides a live broadcast auxiliary data Provide a detailed introduction of a preferred example of the method.

Optionally, as shown in FIG. 3, the method in this embodiment may include the following steps:

S301: Acquire live broadcast auxiliary data during the live broadcast of the live video of the user.

Wherein, the live broadcast auxiliary data includes at least one of the following: live broadcast room data of the anchor user and the anchor fan preference data;

S302: Predict the live broadcast income according to the live broadcast auxiliary data.

Optionally, in this embodiment, in order to further improve the enthusiasm of the host user for live broadcast, the live broadcast income of the host user may also be predicted based on the live broadcast auxiliary data. The specific prediction method may include at least one of the following situations:

When the live broadcast auxiliary data includes the number of viewing fans in the live room data of the host user, it may be that the higher the number of viewing fans, the more the live broadcast revenue is predicted. When the live broadcast auxiliary data includes the change in the number of viewing fans in the live room data of the host user, it may be that if the change in the number of viewing fans is an increase in the number, the more the number increases, the more the live broadcast revenue is predicted; The quantity change is decreasing, and the more the quantity decreases, the less the live broadcast revenue is predicted. When the live broadcast auxiliary data includes the anchor fan preference data, it can be obtained from the anchor user’s user portrait that the anchor is good at live broadcast content and live broadcast format. If the live broadcast content and live broadcast format that the anchor user is good at are more overlapped with the anchor fan’s preference data Higher, the higher the live broadcast revenue is predicted. When the live broadcast auxiliary data includes the site video theme distribution data in the live broadcast platform auxiliary data, it can be judged that the current live broadcast video theme type of the anchor user corresponds to the theme distribution in the station, and the current live video theme type is the video data currently in the site. The smaller the number, the scarcer the current live broadcast theme type, that is, the higher the predicted live broadcast revenue. When the live broadcast auxiliary data includes the number of fans in the live broadcast room in the live broadcast platform auxiliary data, it can be judged that the number of fans watching the current live video of the host user exceeds the value of the average number of fans in the live broadcast room. The larger the excess value, the prediction The higher the live broadcast revenue. When the live broadcast auxiliary data includes the fan preference data in the live broadcast platform auxiliary data, the corresponding method for predicting live broadcast revenue may be similar to the above method for predicting live broadcast revenue based on the anchor fan preference data, which will not be repeated here.

S303: Send the live broadcast auxiliary data and the predicted live broadcast revenue to the anchor user, so that the anchor user optimizes the current live video content based on the live broadcast auxiliary data.

This embodiment provides a method for providing live broadcast auxiliary data. The live broadcast auxiliary data is obtained during the live broadcast of the live video of the host user, and after the live broadcast income is predicted based on the live broadcast auxiliary data, the live broadcast auxiliary data and the predicted live broadcast income value Sent to the anchor user, so that the anchor user optimizes the current live video content based on the live broadcast auxiliary data. The solution of this embodiment can not only provide live broadcast auxiliary data for adjusting the live broadcast strategy to the host user in real time, so as to help the host user make real-time and accurate adjustments to the subsequent live video content, attracting a large number of fans; it can also directly give the host user directly by predicting the live broadcast revenue. Revenue is expected to stimulate and increase the launch rate of anchor users.

FIG. 4 shows a schematic structural diagram of an apparatus for providing live broadcast auxiliary data provided by this embodiment. This embodiment may be suitable for the host user to provide live broadcast auxiliary data for optimizing live video content during the live broadcast of the host user. Case. The device can be implemented by at least one of software and hardware, and the device is integrated in an electronic device that executes the above-mentioned method for providing live broadcast auxiliary data. As shown in FIG. 4, the device can include:

The auxiliary data obtaining module 401 is configured to obtain live broadcast auxiliary data during the live broadcast of the live video of the anchor user; the live broadcast auxiliary data includes at least one of the following: live room data of the anchor user and preference data of the anchor fans;

The auxiliary data sending module 402 is configured to send the live broadcast auxiliary data to the anchor user, so that the anchor user optimizes the current live video content according to the live broadcast auxiliary data.

This embodiment provides an apparatus for providing live broadcast auxiliary data. During the live broadcast of the live video of the host user, the live broadcast auxiliary data including at least one of the following is obtained: the live room data of the host user and the fan preference data of the host, and the The live broadcast auxiliary data is sent to the anchor user, so that the anchor user optimizes the current live video content according to the live broadcast auxiliary data. The solution of this embodiment can provide live broadcast auxiliary data for adjusting the live broadcast strategy to the host user in real time to help the host user make real-time and accurate adjustments to the subsequent live video content, attract a large number of fans, and increase the live broadcast enthusiasm of the host user.

When the live broadcast auxiliary data is the live room data of the host user, the auxiliary data acquisition module 401 is configured to:

Monitor the number of fans in the live broadcast room where the host user is located;

According to the number of watching fans, determine the change in the number of watching fans;

Use at least one of the following as the live room data of the host user: the number of watching fans and the change in the number of watching fans.

When the auxiliary data acquisition module 401 executes the determination of the change in the number of viewing fans according to the number of viewing fans, it is configured as follows:

According to the number of viewing fans, a real-time change curve graph of the number of viewing fans is drawn as the change of the number of viewing fans.

When the auxiliary data acquisition module 401 executes the determination of the change in the number of viewing fans according to the number of viewing fans, it may also be configured as follows:

Determining the change value of the number of watching fans according to the number of watching fans at adjacent moments;

If the change value exceeds the normal change range, then the change value is taken as the change in the number of watching fans.

When the live broadcast auxiliary data is the live room data of the host user, the auxiliary data acquisition module 401 is further configured to:

Perform at least one of the following on the interactive comment content of the live broadcast room where the host user is located: text recognition and semantic recognition; determine a keyword vocabulary, the keyword vocabulary includes at least one of the following: evaluation vocabulary and favorite content vocabulary;

Determining the weight value of the keyword vocabulary according to the frequency of occurrence of the keyword vocabulary in the interactive review content;

The keyword vocabulary and the weight value of the keyword vocabulary are used as the live room data of the host user.

When the live broadcast auxiliary data is the main broadcast fan preference data, the auxiliary data acquisition module 401 is configured to:

Input the detailed data of the anchor user's fan into the user portrait model to obtain the fan portrait of the anchor user's fan;

Acquiring preference feature data from the fan portrait;

The public preference characteristic data is extracted from the preference characteristic data as the anchor fan preference data.

When the auxiliary data acquisition module 401 executes inputting the detailed data of the anchor user's fans into the user portrait model, it is configured as follows:

Judge whether at least one of the ratings and consumption of the anchor users' fans meets the high-quality evaluation criteria;

The detailed data of the anchor user fans that meet the high-quality evaluation criteria are input into the user portrait model.

The auxiliary data acquisition module 401 is also configured to:

Acquire auxiliary data of the live broadcast platform, where the auxiliary data of the live broadcast platform includes at least one of the video theme distribution data in the station, the number of fans in the live broadcast room, and the fan preference data in the station.

The device also includes:

The revenue prediction module is configured to predict the revenue of the live broadcast according to the live broadcast auxiliary data

The auxiliary data sending module 402 is configured to:

Send the live broadcast auxiliary data and the predicted live broadcast revenue to the anchor user.

For content not described in detail in this embodiment, reference may be made to all the above embodiments, and this embodiment has the same effect as all the above embodiments.

Next, refer to FIG. 5, which shows a schematic structural diagram of an electronic device suitable for implementing this embodiment. The electronic device in this embodiment may be a device corresponding to the back-end live broadcast platform of the application, or a mobile terminal device with an application client installed. The electronic equipment may include, but is not limited to, mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (PAD), portable multimedia players (Portable Media Player, PMP), vehicle-mounted A mobile terminal such as a terminal (for example, a car navigation terminal) and a fixed terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in FIG. 5 is only an example, and should not bring any limitation to the function and scope of use of this embodiment.

As shown in FIG. 5, the electronic device may include a processing device 501, such as a central processing unit, a graphics processor, etc. The processing device 501 may be based on a program stored in a read-only memory (Read-Only Memory, ROM) 502 or from The storage device 508 loads a program in a random access memory (Random Access Memory, RAM) 503 to execute various appropriate actions and processes. In the RAM 503, various programs and data required for the operation of the electronic device are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input/output (Input/Output, I/O) interface 505 is also connected to the bus 504.

Generally, the following devices can be connected to the I/O interface 505: including input devices 506 such as touch screens, touch panels, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; including, for example, liquid crystal displays (LCD) Output devices 507 such as speakers, vibrators, etc.; storage devices 508 such as magnetic tapes, hard disks, etc.; and communication devices 509. The communication device 509 may allow the electronic device to perform wireless or wired communication with other devices to exchange data. Although FIG. 5 shows an electronic device with multiple devices, it should be understood that it is not required to implement or have all of the illustrated devices. It may alternatively be implemented or provided with more or fewer devices.

According to this embodiment, the process described above with reference to the flowchart can be implemented by a computer software program. For example, this embodiment includes a computer program product, including a computer program carried on a non-transitory computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of this embodiment are executed.

It should be noted that the aforementioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may include, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the above, for example. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, RAM, ROM, Erasable Programmable Read-Only Memory, EPROM) or flash memory, optical fiber, compact Disc Read-Only Memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium. The computer-readable signal medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device . The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, radio frequency (RF), etc., or any suitable combination of the foregoing.

In some embodiments, the electronic device can communicate with any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can communicate with any form or medium of digital data ( For example, communication networks) are interconnected. Examples of communication networks include Local Area Network (LAN), Wide Area Network (WAN), the Internet (for example, the Internet), and end-to-end networks (for example, ad hoc end-to-end networks), and any currently available Know or develop a network in the future.

The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.

The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the internal process of the electronic device is executed: in the process of broadcasting the user's live video, the live broadcast auxiliary data is obtained; The live broadcast auxiliary data includes the live room data of the anchor user and/or the fan preference data of the anchor; the live broadcast auxiliary data is sent to the anchor user, so that the anchor user optimizes the current live video content according to the live broadcast auxiliary data.

The computer program code used to perform the operations of the present disclosure may be written in one or more programming languages or a combination thereof. The above-mentioned programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and Including conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a LAN or WAN, or may be connected to an external computer, for example, using an Internet service provider to connect through the Internet.

The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions, and operations of the system, method, and computer program product according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logical function Executable instructions. It should also be noted that, in some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown in succession can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.

The units involved in the description of this embodiment can be implemented in software or hardware. Among them, the name of the unit does not constitute a limitation on the unit itself under certain circumstances.

The functions described hereinabove may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), and application specific standard products (Application Specific Standard Product, ASSP), System on a Chip (SOC), Complex Programmable Logic Device (CPLD), etc.

In the context of the present disclosure, a computer-readable medium may be a tangible medium, and the computer-readable medium may contain or store a program for use by the instruction execution system, apparatus, or device or in combination with the instruction execution system, apparatus, or device. According to one or more embodiments of the present disclosure, a method for providing live broadcast auxiliary data is provided, the method including:

According to one or more embodiments of the present disclosure, in the above method, when the live broadcast auxiliary data is the live room data of the host user, acquiring the live broadcast auxiliary data includes:

According to one or more embodiments of the present disclosure, in the above method, determining the change in the number of viewing fans according to the number of viewing fans includes:

The keyword vocabulary and its weight value are used as the live room data of the host user.

According to one or more embodiments of the present disclosure, in the above method, when the live broadcast auxiliary data is the main broadcast fan preference data, acquiring the live broadcast auxiliary data includes:

Acquiring preference feature data from the fan portrait;

According to one or more embodiments of the present disclosure, in the above method, inputting detailed data of the anchor user's fans into the user portrait model includes:

According to one or more embodiments of the present disclosure, in the above method, acquiring live broadcast auxiliary data includes:

Acquire auxiliary data of the live broadcast platform, where the auxiliary data of the live broadcast platform includes at least one of the video topic distribution data in the station, the number of fans in the live broadcast room, and the fan preference data in the station.

According to one or more embodiments of the present disclosure, in the above method, after obtaining the live broadcast auxiliary data, the method further includes:

According to the live broadcast auxiliary data, the live broadcast income is predicted.

According to one or more embodiments of the present disclosure, in the above method, sending the live broadcast auxiliary data to the anchor user includes:

According to one or more embodiments of the present disclosure, a device for providing live broadcast auxiliary data is provided, which includes:

According to one or more embodiments of the present disclosure, when the live broadcast auxiliary data is the live room data of the host user, the auxiliary data acquisition module in the above-mentioned apparatus is configured to:

At least one of the number of viewing fans and the change of the number of viewing fans is used as the live room data of the anchor user.

According to one or more embodiments of the present disclosure, when the auxiliary data acquisition module in the above-mentioned device executes the determination of the change in the number of viewing fans according to the number of viewing fans, it is configured to:

According to one or more embodiments of the present disclosure, when the auxiliary data acquisition module in the above-mentioned device executes the determination of the change in the number of viewing fans according to the number of viewing fans, it may also be configured as:

According to one or more embodiments of the present disclosure, when the live broadcast auxiliary data is the live room data of the host user, the auxiliary data acquisition module in the above-mentioned apparatus is further configured to:

According to one or more embodiments of the present disclosure, when the live broadcast auxiliary data is the main broadcast fan preference data, the auxiliary data acquisition module in the above-mentioned device is configured to:

Acquiring preference feature data from the fan portrait;

According to one or more embodiments of the present disclosure, when the auxiliary data acquisition module in the above-mentioned device executes inputting detailed data of the anchor user's fans into the user portrait model, it is configured to:

According to one or more embodiments of the present disclosure, the auxiliary data acquisition module in the above-mentioned device is further configured to:

According to one or more embodiments of the present disclosure, the above-mentioned device further includes:

The revenue prediction module is configured to: predict the revenue of the live broadcast according to the live broadcast auxiliary data

According to one or more embodiments of the present disclosure, the auxiliary data sending module in the above-mentioned device is specifically configured as follows:

According to an electronic device provided by one or more embodiments of the present disclosure, the electronic device includes:

One or more processors;

Memory, configured to store one or more programs;

When the one or more programs are executed by the one or more processors, the one or more processors implement the method for providing live broadcast auxiliary data according to any embodiment of the present disclosure.

According to a readable medium provided by one or more embodiments of the present disclosure, a computer program is stored on the readable medium, and when the program is executed by a processor, the live broadcast auxiliary data as described in any embodiment of the present disclosure is realized. Provide methods.

Although the operations are depicted in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable subcombination.

Claims

A method for providing live broadcast auxiliary data, including:

During the live broadcast of the live video of the anchor user, the live broadcast auxiliary data is obtained; the live broadcast auxiliary data includes at least one of the following: live room data of the anchor user and the anchor fan preference data;

The live broadcast auxiliary data is sent to the anchor user, so that the anchor user optimizes the current live video content according to the live broadcast auxiliary data.
The method according to claim 1, wherein when the live broadcast auxiliary data is the live room data of the host user, acquiring the live broadcast auxiliary data comprises:

Monitor the number of fans in the live broadcast room where the host user is located;

According to the number of watching fans, determine the change in the number of watching fans;

At least one of the following is used as the live room data of the host user: the number of watching fans and the change in the number of watching fans.
The method according to claim 2, wherein determining the change in the number of viewing fans according to the number of viewing fans comprises:

According to the number of viewing fans, a real-time change curve graph of the number of viewing fans is drawn as the change of the number of viewing fans.
The method according to claim 2, wherein determining the change in the number of viewing fans according to the number of viewing fans comprises:

Determining the change value of the number of watching fans according to the number of watching fans at adjacent moments;

If the change value exceeds the normal change range, then the change value is taken as the change in the number of watching fans.
The method according to any one of claims 1 to 4, wherein, when the live broadcast auxiliary data is the live room data of the host user, acquiring the live broadcast auxiliary data includes:

Perform at least one of the following on the interactive comment content of the live broadcast room where the host user is located: text recognition and semantic recognition;

Determine a keyword vocabulary, which includes at least one of the following: evaluation vocabulary and favorite content vocabulary;

Determining the weight value of the keyword vocabulary according to the frequency of occurrence of the keyword vocabulary in the interactive review content;

The keyword vocabulary and the weight value of the keyword vocabulary are used as the live room data of the host user.
The method according to claim 1, wherein when the live broadcast auxiliary data is the main broadcast fan preference data, acquiring the live broadcast auxiliary data comprises:

Input the detailed data of the anchor user's fan into the user portrait model to obtain the fan portrait of the anchor user's fan;

Acquiring preference feature data from the fan portrait;

The public preference characteristic data is extracted from the preference characteristic data as the anchor fan preference data.
The method according to claim 6, wherein inputting detailed data of the anchor user's fans into the user portrait model comprises:

Judge whether at least one of the ratings and consumption of the anchor users' fans meets the high-quality evaluation criteria;

The detailed data of the anchor user fans that meet the high-quality evaluation criteria are input into the user portrait model.
The method according to any one of claims 1 to 7, wherein obtaining live broadcast auxiliary data further comprises:

Acquire auxiliary data of the live broadcast platform, where the auxiliary data of the live broadcast platform includes at least one of the video theme distribution data in the station, the number of fans in the live broadcast room, and the fan preference data in the station.
The method according to any one of claims 1 to 8, wherein after obtaining the live broadcast auxiliary data, the method further comprises:

According to the live broadcast auxiliary data, the live broadcast income is predicted.
The method according to claim 9, wherein sending the live broadcast auxiliary data to the host user comprises:

Sending the live broadcast auxiliary data and the predicted live broadcast revenue to the anchor user.
A device for providing live broadcast auxiliary data includes:

The auxiliary data obtaining module is configured to obtain live broadcast auxiliary data during the live broadcast of the live video of the anchor user; the live broadcast auxiliary data includes at least one of the following: live room data of the anchor user and preference data of the anchor fans;

The auxiliary data sending module is configured to send the live broadcast auxiliary data to the anchor user, so that the anchor user optimizes the current live video content according to the live broadcast auxiliary data.
An electronic device including:

One or more processors;

Memory, configured to store one or more programs;

When the one or more programs are executed by the one or more processors, the one or more processors realize the method for providing live broadcast auxiliary data according to any one of claims 1-10.
A readable medium on which a computer program is stored, wherein when the program is executed by a processor, the method for providing live broadcast auxiliary data according to any one of claims 1-10 is realized.